Item Attribute Collection

1. A system comprising: a wall element having a plurality of openings of different sizes to receive one or more objects to be sorted in a plurality of containers; a plurality of chutes, each chute coupling one of the plurality of openings with one of the plurality of containers; at least one camera positioned in a first chute of the plurality of chutes, the at least one camera to generate scan data for a first object deposited into a first opening corresponding to the first chute; and a processing device to: receive, from the at least one camera, first scan data corresponding to a plurality of objects comprising the first object; apply object detection processing to the first scan data to identify and classify the plurality of objects; generate, based on the object detection processing of the first scan data, (1) type data indicative of an object type of one of the plurality of objects, (2) sort data indicative of the one of the plurality of chutes in which one of the plurality of objects was detected and (3) attribute data indicative of a shape of an object and packaging data corresponding to one of the plurality of objects; add the plurality of objects to an inventory based on the type data; determine a performance metric based on a comparison of first attribute data of the first object of the plurality of objects and first sort data indicating the first chute comprising the at least one camera that detected a presence of the first object, wherein the performance metric comprises a score indicating a size of the first chute corresponds to the first attribute data of the first object; and provide an output indicative of the performance metric.

2. The system of claim 1 , wherein the output is an audiovisual output comprising at least one of a colored light, an error sound or a displayed score.

3. A method comprising: receiving, from a camera positioned in a first chute coupled to an opening of a wall element, scan data associated with an object deposited into the opening corresponding to the first chute; applying object detection processing to the scan data to identify and classify the object; generating, based on the object detection processing of the scan data, type data indicative of an object type of the object, sort data indicative of the first chute in which the object was detected, and attribute data indicative of a shape of the object and packaging data corresponding to the object; adding an entry for the object to an inventory data structure based on the type data; and storing the attribute data corresponding to the object in an attribute data structure based on the type data, wherein the attribute data structure associates at least a first object type with a first plurality of values of the attribute data and a second object type with a second plurality of values of the attribute data.

4. The method of claim 3 , wherein the scan data comprises a plurality of images of the object.

5. The method of claim 4 , wherein the camera is one of a plurality of cameras oriented to surround the object and generate the plurality of images.

6. The method of claim 3 , wherein the attribute data of the object comprises at least one of a size of the object or a color of the object.

7. The method of claim 3 , wherein the attribute data of the object comprises a packaging parameter of the object.

8. The method of claim 3 , further comprising: receiving sort data indicative of one of a plurality of chutes in which imaging-of the object occurred; determining a first value of the attribute based on the one of the plurality of chutes; determining a second value of the attribute based on the attribute data; and determining an accuracy metric based on the first value and the second value.

9. The method of claim 3 , wherein: receiving the scan data comprises receiving a plurality of scan data of a plurality of objects; generating the type data and the attribute data comprises generating, based on the object detection processing of the plurality of scan data, a plurality of type data indicative of a plurality of object types of the plurality of objects and a plurality of attribute data indicative of a plurality of values of one or more attributes of the plurality of objects; adding the entry for the object comprises adding a plurality of entries for the plurality of objects to the inventory data structure based on the plurality of type data; and storing the value comprises storing the plurality of values of the attribute of the plurality of objects in the attribute data structure based on the plurality of type data.

10. The method of claim 9 , further comprising: receiving a plurality of sort data indicative of respective ones of a plurality of chutes in which the scan data was generated; determining a performance metric based on the plurality of sort data and the plurality of attribute data; and providing an indication of the performance metric.

11. The method of claim 10 , wherein the performance metric comprises an accuracy metric indicative of a percentage of the plurality of sort data that match the plurality of attribute data.

12. The method of claim 10 , wherein the performance metric comprises a speed metric indicative of a rate at which the plurality of sort data was generated.

13. The method of claim 10 , wherein providing an indication of the performance metric comprises generating an audiovisual output.

14. A non-transitory computer-readable medium having instructions encoded thereon which, when executed by a processing device, cause the processing device to perform operations comprising: receiving, from a camera positioned in a first chute coupled to an opening of a wall element, a plurality of scan data identifying a plurality of objects comprising a first object; applying object detection processing to the scan data to identify and classify the plurality of objects; generating, based on the object detection processing of the plurality of scan data, type data indicative of a plurality of object types of the plurality of objects and a plurality of attribute data indicative of a size and a shape of an object and packing data corresponding to plurality of values of an attribute of the plurality of objects; adding a plurality of entries for the plurality of objects to an inventory data structure based on the type data; comparing, by the processing device, the plurality of values associated with one of the plurality of object types with a previously generated plurality of values associated the one of the plurality of object types stored in an attribute data structure; and determining, by the processing device, that the attribute has changed for the one of the plurality of object types based on the comparison.

15. The non-transitory computer-readable medium of claim 14 , wherein determining that the attribute has changed comprises determining that a packaging associated with the one of the plurality of object types has changed.

16. The non-transitory computer-readable medium of claim 14 , wherein determining that the attribute has changed comprises determining that a size or shape of objects associated with the one of the plurality of object types has changed.

17. The non-transitory computer-readable medium of claim 14 , the operations further comprising generating, before receiving the plurality of scan data, the previously generated plurality of values by: receiving a previous plurality of scan data of a previous plurality of objects; generating, based on the previous plurality of scan data, a previous plurality of type data indicative of a previous plurality of object types of the previous plurality of objects and a previous plurality of attribute data indicative of a previous plurality of values of the attribute of the previous plurality of objects; adding a plurality of previous entries for the previous plurality of objects to the inventory data structure based on the previous plurality of type data; and storing the previous plurality of values of the attribute of the previous plurality of objects in the attribute data structure based on the previous plurality of type data.